{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:GFDHZAUZAN4JTUX7AHS5V4HVXE","short_pith_number":"pith:GFDHZAUZ","schema_version":"1.0","canonical_sha256":"31467c8299037899d2ff01e5daf0f5b904d0736f5cd8eb18b0b40d9d73dda53b","source":{"kind":"arxiv","id":"1702.08670","version":1},"attestation_state":"computed","paper":{"title":"On architectural choices in deep learning: From network structure to gradient convergence and parameter estimation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Sathya N Ravi, Vamsi K Ithapu, Vikas Singh","submitted_at":"2017-02-28T07:05:27Z","abstract_excerpt":"We study mechanisms to characterize how the asymptotic convergence of backpropagation in deep architectures, in general, is related to the network structure, and how it may be influenced by other design choices including activation type, denoising and dropout rate. We seek to analyze whether network architecture and input data statistics may guide the choices of learning parameters and vice versa. Given the broad applicability of deep architectures, this issue is interesting both from theoretical and a practical standpoint. Using properties of general nonconvex objectives (with first-order inf"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"1702.08670","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-02-28T07:05:27Z","cross_cats_sorted":["math.OC","stat.ML"],"title_canon_sha256":"d801d6fa0d7a8b06d37a144833d0299e4dc7b56e3607e11ab6c7bce05086998b","abstract_canon_sha256":"14a005f7a946ab9435d4f21bb76f291db5c1aa6c1f41740e79882409e6446241"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:49:48.138836Z","signature_b64":"KVOC66AIyRZ9pbBMC+t8rPgwpVIDyXFWMPQ35kGwiZpE1b9m/+EkZJwSfwj1hLuvzMqkzAwqgSkiruskrraRCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"31467c8299037899d2ff01e5daf0f5b904d0736f5cd8eb18b0b40d9d73dda53b","last_reissued_at":"2026-05-18T00:49:48.138332Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:49:48.138332Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"On architectural choices in deep learning: From network structure to gradient convergence and parameter estimation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Sathya N Ravi, Vamsi K Ithapu, Vikas Singh","submitted_at":"2017-02-28T07:05:27Z","abstract_excerpt":"We study mechanisms to characterize how the asymptotic convergence of backpropagation in deep architectures, in general, is related to the network structure, and how it may be influenced by other design choices including activation type, denoising and dropout rate. We seek to analyze whether network architecture and input data statistics may guide the choices of learning parameters and vice versa. Given the broad applicability of deep architectures, this issue is interesting both from theoretical and a practical standpoint. Using properties of general nonconvex objectives (with first-order inf"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1702.08670","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"1702.08670","created_at":"2026-05-18T00:49:48.138410+00:00"},{"alias_kind":"arxiv_version","alias_value":"1702.08670v1","created_at":"2026-05-18T00:49:48.138410+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1702.08670","created_at":"2026-05-18T00:49:48.138410+00:00"},{"alias_kind":"pith_short_12","alias_value":"GFDHZAUZAN4J","created_at":"2026-05-18T12:31:15.632608+00:00"},{"alias_kind":"pith_short_16","alias_value":"GFDHZAUZAN4JTUX7","created_at":"2026-05-18T12:31:15.632608+00:00"},{"alias_kind":"pith_short_8","alias_value":"GFDHZAUZ","created_at":"2026-05-18T12:31:15.632608+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GFDHZAUZAN4JTUX7AHS5V4HVXE","json":"https://pith.science/pith/GFDHZAUZAN4JTUX7AHS5V4HVXE.json","graph_json":"https://pith.science/api/pith-number/GFDHZAUZAN4JTUX7AHS5V4HVXE/graph.json","events_json":"https://pith.science/api/pith-number/GFDHZAUZAN4JTUX7AHS5V4HVXE/events.json","paper":"https://pith.science/paper/GFDHZAUZ"},"agent_actions":{"view_html":"https://pith.science/pith/GFDHZAUZAN4JTUX7AHS5V4HVXE","download_json":"https://pith.science/pith/GFDHZAUZAN4JTUX7AHS5V4HVXE.json","view_paper":"https://pith.science/paper/GFDHZAUZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1702.08670&json=true","fetch_graph":"https://pith.science/api/pith-number/GFDHZAUZAN4JTUX7AHS5V4HVXE/graph.json","fetch_events":"https://pith.science/api/pith-number/GFDHZAUZAN4JTUX7AHS5V4HVXE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GFDHZAUZAN4JTUX7AHS5V4HVXE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GFDHZAUZAN4JTUX7AHS5V4HVXE/action/storage_attestation","attest_author":"https://pith.science/pith/GFDHZAUZAN4JTUX7AHS5V4HVXE/action/author_attestation","sign_citation":"https://pith.science/pith/GFDHZAUZAN4JTUX7AHS5V4HVXE/action/citation_signature","submit_replication":"https://pith.science/pith/GFDHZAUZAN4JTUX7AHS5V4HVXE/action/replication_record"}},"created_at":"2026-05-18T00:49:48.138410+00:00","updated_at":"2026-05-18T00:49:48.138410+00:00"}